Beware explanations from AI in health care
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
The benefits of explainable artificial intelligence are not what they appear
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“An example includes a diagnostic algorithm that uses images of patients’ skin to detect skin cancer possibly failing in the summer when more people with more sun exposure have a different color tone, compared to the skin tones used in the training data [45].”
From Bias in artificial intelligence algorithms and recommendations for mitigation (2023) · cites this paper as [45]
In the citing paper
“Post-hoc interpretability methods are only approximations and do not accurately depict the correct model behavior and therefore compromise trust in the explanations [5,110].”
From Transparency of deep neural networks for medical image analysis: A review of interpretability methods (2022) · cites this paper as [5]
In the citing paper
“Since post-hoc explanation methods are only approximations, they cannot ensure complete accountability [5].”
From Transparency of deep neural networks for medical image analysis: A review of interpretability methods (2022) · cites this paper as [5]
Citations
Cites
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Artificial intelligence in healthcare
Yu, K.-H., Beam, A. L., & Kohane, I. S. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0305-z · Cited by 2,817
Dietvorst, B. J., Simmons, J. P., & Massey, C. (2018) · Management Science · doi:10.1287/mnsc.2016.2643 · Cited by 1,230
Benjamens, S., Dhunnoo, P., & Meskó, B. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00324-0 · Cited by 1,215
Ethical and legal challenges of artificial intelligence-driven healthcare
Gerke, S., Minssen, T., & Cohen, G. (2020) · Artificial Intelligence in Healthcare · doi:10.1016/b978-0-12-818438-7.00012-5 · Cited by 1,170
Self-citationMarkus, A. F., Kors, J. A., & Rijnbeek, P. R. (2021) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2020.103655 · Cited by 811
Muehlematter, U. J., Daniore, P., & Vokinger, K. N. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30292-2 · Cited by 665
Intelligible models for classification and regression
Lou, Y., Caruana, R., & Gehrke, J. (2012) · Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2339530.2339556 · Cited by 547
Research works printed but not linked: 2
- S. Wachter, B. Mittelstadt, C. Russell, Harv. J. Law Technol. 31, 841 (2018).
- R. M. Hamm, S. L. Smith, J. Fam. Pract. 47, 44 (1998).
Cited by
Items 201–282 of 282
Three Strategies for Salvaging Explanatory Value in Deep Neural Network Modeling
Verreault-Julien, P. (2025) · Routledge eBooks · doi:10.4324/9781003342816-13 · Cited by 2
Knowledge Engineering in the Long Game of Artificial Intelligence: The Case of Speech ActsPreprint
McShane, M. J., English, J., & Nirenburg, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.01040 · Cited by 1
A Trustworthy View on XAI Method EvaluationPreprint
LI, D., Liu, Y., Huang, J., & Wang, Z. (2022) · doi:10.36227/techrxiv.21067438.v2 · Cited by 2
Xia, H.-J., Chang, J. C., Nowak, S. A., Mahajan, S., Mahajan, R., Chang, T. L., & Chow, C. (2023) · Machine Learning in Health Care · doi:10.48550/arxiv.2304.09981 · Cited by 3
Solaiman, B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4886518 · Cited by 1
Editorial: Health services and the 4th industrial revolution
van de Klundert, J. J., Mankowski, M. A., & de Vries, H. (2025) · Frontiers in Health Services · doi:10.3389/frhs.2025.1646779 · Cited by 1
Investigating the Risks of Algorithmic Bias and Explainability Failures in Credit Risk ModelsPreprint
Shah, I. H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5361937 · Cited by 1
Mai, M. V., Ozkaynak, M., Marquard, J. L., Simonson, R. J., Holden, R. J., Barton, H. J., Catchpole, K., Jamil, M., Brauer, S., & Kandaswamy, S. (2026) · medRxiv · doi:10.64898/2026.01.18.26344350 · Cited by 1
Karr, A. F., Hauzel, J., Menon, P. G., Porter, A., & Schaefer, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.06677
(2023) · Elsevier eBooks · doi:10.1016/b978-0-323-90534-3.16001-9
AI without networksPreprint
Mitra, P. P., & Sire, C. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.12.09.570922
BioAutoML: Democratizing Machine Learning in Life Sciences
Bonidia, R. P. (2024) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.55.2024.tde-01042024-092414
AI Without NetworksPreprint
Mitra, P. P., & Sire, C. (2024) · Research Square · doi:10.21203/rs.3.rs-3721935/v1
Transforming healthcare: A comprehensive review of AI applications in medical care
Raut, A. D., Kale, S. R., & Gawande, S. (2024) · DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry (IDICAIHEI) · doi:10.1109/idicaiei61867.2024.10842739 · Cited by 1
Blockchain and smart contracts for wearable health sensing
Cedeño, J. R., Sánchez-Torres, C. E., & Favela, J. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-36370-2.00017-7
A neurosymbolic approach to authorship anonymization
McShane, M. J., Nirenburg, S., Arndt, C., Oruganti, S., & English, J. (2025) · Cognitive Systems Research · doi:10.1016/j.cogsys.2025.101335
Operationalizing AI Ethics - A Quantifiable Framework for Implementation and Assessment
Kumar, D., Singla, B. S., & Choudhary, R. K. (2025) · IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi64286.2025.10985308
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0014
Algorithmically Enhanced Misperceptions
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0005
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.002.0008
Algorithmic Price Discrimination: Extensions
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0003
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0001
Ex Post Policing and Ex Ante Regulation
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0011
The Right to Algorithmic Transparency
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0010
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0013
Regulating Preconditions for Algorithmic Harm
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0009
Applying the Reforms to the Different Harm Categories
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0012
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0007
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0006 · Cited by 1
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0004
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0015
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.002.0004
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.002.0005
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.003.0008
Bar‐Gill, O., & Sunstein, C. R. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197778197.002.0003
Forschungsintegrität in aufkommenden Technologien: Geneditierung und KI-Forschung in der Medizin
Redman, B. K. (2025) · Springer eBooks · doi:10.1007/978-3-031-92469-9_9
Medical Artificial Intelligence
Grote, T. (2025) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780197625835.013.0033
Skepticism about Post-hoc Explainability and Idealized Models
Knoks, A., & Raleigh, T. (2025) · The British Journal for the Philosophy of Science · doi:10.1086/739298
Hossain, E., Aziz, M. N., Alam, M. J., Kakon, M. I., & Haque, F. (2025) · Journal of Computer Science and Information Technology · doi:10.61424/jcsit.v2i2.469
Standing on the shoulders of giants: A review of reviews on health information behavior
Zhang, X., Zhao, Y., & Yang, F. (2025) · Library & Information Science Research · doi:10.1016/j.lisr.2025.101380
Humans’ Use of AI-Assistance: The Effect of Loss Aversion on Willingness to Delegate DecisionsPreprint
Buckman, J. R. (2024) · OSF Preprints (OSF Preprints) · doi:10.17605/osf.io/z6eqx
The Ethical Implications of AI in Healthcare
Hirmiz, R. (2024) · YorkSpace (York University) · Cited by 4
Through a glass, darkly: Transparency and military AI systems
Marijan, B. (2025) · Econstor (Econstor) · Cited by 3
Research Group Critical Information Infrastructures (cii), Sunyaev, A., Sturm, B., Du, G., Schmidt-Kraepelin, M., Kannengießer, N., Toussaint, P. A., Thiebes, S., & Heß, Y. (2025) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000185402
Artificial Intelligence and Linguistics
McShane, M. J., & Nirenburg, S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-323-95504-1.01206-0
Isolating variable effects in supervised machine learning illustrated in educational data mining
Filho, R. L. C. S. (2024) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)
أزمة التشاؤمية في حقل أخلاقيات الذكاء الاصطناعي
Königs, P. (2026) · تبين للدراسات الفكرية و الثقافية · doi:10.31430/vifv3059
Challenges and Applications of Integrating Artificial Intelligence in Orthodontics
Obaidat, L., Mohawesh, R., Salameh, H. B., Al-Khatib, R. M., & Dwaeikat, T. (2025) · International Conference on Intelligent Computing, Communication, Networking and Services (ICCNS) · doi:10.1109/iccns66249.2025.11428343
All you need is…. justification: algorithmic justifiability trumps transparency
Muralidharan, A., & Savulescu, J. (2026) · Ethics and Information Technology · doi:10.1007/s10676-026-09892-3 · Cited by 2
Thinking through responsibilities in AI-driven healthcare
Ferlito, B. (2026) · Ghent University Academic Bibliography (Ghent University)
Perez-Torrents, J. (2024) · theses.fr (ABES) · doi:10.70675/97d0e67ez9ba4z4494z98d7z5a282887792f · Cited by 3
Huang, Q. E., Williams, S. A., & Helle, S. (2026) · The Journal of Rural Health · doi:10.1111/jrh.70144
The moral impact of delegating to artificial intelligence
Wei, T., Wenrui, Z., Zhen, L., & Dandan, Z. (2026) · Advances in Psychological Science · doi:10.3724/sp.j.1042.2026.1084
Khatun, S. (2026) · Studies in big data · doi:10.1007/978-3-032-18871-7_18
Cognitive Stitching: Informal AI Integration in Everyday Clinical ReasoningPreprint
Guo, Z. (2026) · Research Square · doi:10.21203/rs.3.rs-9095240/v1
On the disruptiveness of interdisciplinary research and artificial intelligence for science
Tang, K., Zhang, X., & Li, B. (2026) · Scientometrics · doi:10.1007/s11192-026-05618-w
The age of Articicial Intelligence: a thematic review on AI agent and explainable AI
de Carvalho, M. F., Dias, M. D. O., & Junior, D. S. D. S. (2026) · Revista edUCA - Revista Multidisciplinar da Faculdade Católica Paulista · doi:10.54901/educa.v9-275
Cognitive Dependency on Clinical Decision Support Systems: Implications for Diagnostic Reasoning
Hayati, Z., Yaman, I., & Sya'diah, Y. (2026) · Asian Journal of Healthcare Analytics · doi:10.55927/ajha.v5i1.16251
Marfo, R., & Veselý, A. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-07577-2
Connelly, L. C., Pedersen, T. M., Øvlisen, K., Bilstrup, K.-E. K., Petersen, M. G., & Nyrup, R. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812233
Alkhnbashi, O. S., Mohammad, R., Khyriem, C., Hauns, S., Singh, A., Khan, I., Gomez, R. L., Ramachandran, R., Albedwawi, M. H., AbdulRahim, M. M., et al. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11634-2
Algorithmic Opacity, Clinical Justification, and the Duty of Candour in AI-Assisted Care
Ibrahim, H., & Hudson, Z. (2026) · Cureus · doi:10.7759/cureus.113364
Morales, S., Kumar, N., Georgiou, E., & Garcia, C. (2024) · Pharmacophore · doi:10.51847/qdjn456xbw
Ramirez, C., Torres, E., Ortega, P., & Mendes, S. (2026) · Pharmacophore · doi:10.51847/2pdevvb1uu
Miller, R., Schmidt, L., Walker, J., & Taylor, E. (2025) · Pharmacophore · doi:10.51847/1ae49rlxig
Mdluli, N. T., Chang, Y., Wu, C.-H., & Cheng, W.-J. (2026) · doi:10.2196/preprints.108578
Gauthier-Maxence, C., & Milcent, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35387-0_3
Liu, O. (2026) · Stout in Medical Science Biology and Chemistry · doi:10.61424/k0qrad59
Building an Explainability Contract between Clinical Algorithms and Practicing Pharmacists
Anderson, M., Wong, L., & Lee, S. (2025) · Archives of Pharmacy Practice · doi:10.51847/rgnlce8u0w
Frederickson, K. L., Li, D., Edrich, O. D., Bhatia, A. C., Adunyah, S. E., & Wang, Q. (2026) · Research Square · doi:10.21203/rs.3.rs-10500601/v2
Sustainable Explainability in Medical Imaging: An Agentic Explainable AI Framework
Muhammad, D., Salman, M., & Bendechache, M. (2026) · Information systems engineering and management · doi:10.1007/978-3-032-22426-2_11
Mohanty, A. K., Panda, B., & Patra, P. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-33512-9.00017-2
Kulkarni, S., Joshi, M., & Patil, R. (2024) · Journal of Artificial Intelligence for Healthcare Systems · doi:10.68159/b352704680
Deep Learning Integration in Clinical Decision Infrastructure: A Systems-Oriented Review
Dupont, C., & Martin, J. (2023) · Journal of Artificial Intelligence for Healthcare Systems · doi:10.68159/n174260851
Social Perception and Trust Pathways in Generative AI: Implications for Delegation and Decision Aid
Noh, H., Rim, H. B., & Kim, B. (2026) · SAGE Open · doi:10.1177/21582440261490992
ARTIFICIAL INTELLIGENCE IN EMERGENCY MEDICAL CARE: ETHICAL AND LEGAL ISSUES
Godovanets, O. S., Nechytailo, О. Y., Dronyk, K., Андрущак, А. В., & Gerush, N. (2026) · Neonatology surgery and perinatal medicine · doi:10.24061/2413-4260.xvi.3.61.2026.2
Weber, A., Müller, T., Nair, P., & Anderson, J. (2026) · Asian Journal of Ethics in Health and Medicine · doi:10.51847/y4wmkd6kz5
Stylios, I., Kokolakis, S., Damopoulos, D., Tzallas, A. T., & Gritzalis, S. (2026) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp6050174
A Modality-Adaptive Software Architecture for Explainable Clinical Decision Support
Lissovoy, D., Khalyk, A., Oralov, A., Mustafin, R., Kenzhegaliyev, A., & Ali, H. (2026) · GlobeIS International Journal of Global Information Systems · doi:10.66395/globeis.25
Invisible hands of AI: How statistical methods shape trustworthy and ethical healthcare technologies
Kalina, J. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45156-0.00005-4
Software as a medical device and answerable clinical care: dignity at the interface
Liu, B. (2026) · Medicine Health Care and Philosophy · doi:10.1007/s11019-026-10414-7
Metadata
- Authors
- Babic, B., Gerke, S., Evgeniou, T., & Cohen, I. G.
- Affiliations
- University of Toronto (CA)
- Pennsylvania State University (US)
- INSEAD (FR)
- Harvard University (US)
- Venue
- Science
- Published
- 2021-07-16
- Volume
- 373
- Issue
- 6552
- Pages
- 284-286
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W3183015861
- Cited by
- 252
- References
- 14
- Citations by year
- 2026: 46 · 2025: 66 · 2024: 57 · 2023: 42 · 2022: 34 · 2021: 6
- FWCI
- 12.29
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Science (publishedVersion)
- PubMed (publishedVersion)
- bepress Legal Repository (submittedVersion)
- eYLS (Yale Law School) (submittedVersion)
- Funders
- Novo Nordisk Fonden (NNF17SA0027784)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Keywords
- explainable AI, health care, AI explanations, clinical decision support, AI limitations
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.